Skip to main content

Documentation Index

Fetch the complete documentation index at: https://superwire.dev/llms.txt

Use this file to discover all available pages before exploring further.

Ollama is useful for local development when you do not want to call a remote provider. 
provider local_llm from ollama {
    endpoint: "http://localhost:11434"
}

model local_fast from local_llm {
    id: "llama3.1"
}

agent reply {
    model: model.local_fast
    instruction: "Reply to {{ input.message }}."

    output {
        message: string
    }
}
The executor container must be able to reach the Ollama host. In Docker deployments, localhost refers to the container itself, not necessarily your host machine.